TY -的A2 -米利,米歇尔AU -李,明永盟——一个Ziye盟——魏Qinmin盟——香,凯悦AU - Ma,燕PY - 2019 DA - 2019/10/09 TI -三重态深哈希共同监督损失基于深层神经网络SP - 8490364六世- 2019 AB -近年来,多媒体数据的爆炸从搜索引擎、社交媒体,而电子商务平台迫切需要海量大数据的快速检索方法。哈希算法由于其存储成本低、查询速度快等优点，在大规模高维数据搜索中得到了广泛的应用。由于深度学习在很多领域的巨大成功，深度学习方法已经被引入到哈希检索中，它使用深度神经网络同时学习图像特征和哈希代码。与传统的哈希算法相比，该算法具有更好的性能。然而，现有的深度哈希方法存在一定的局限性;例如，大多数方法只考虑一种监督损失，导致监督信息利用不足。针对这一问题，本文提出了一种基于卷积神经网络(JLTDH)的具有联合监督损失的三重深度哈希方法。所提出的JLTDH方法结合了三重似然损失和线性分类损失;此外，还采用了三组监督标签，比点式和两两式的监督标签包含更丰富的监督信息。 At the same time, in order to overcome the cubic increase in the number of triplets and make triplet training more effective, we adopt a novel triplet selection method. The whole process is divided into two stages: In the first stage, taking the triplets generated by the triplet selection method as the input of the CNN, the three CNNs with shared weights are used for image feature learning, and the last layer of the network outputs a preliminary hash code. In the second stage, relying on the hash code of the first stage and the joint loss function, the neural network model is further optimized so that the generated hash code has higher query precision. We perform extensive experiments on the three public benchmark datasets CIFAR-10, NUS-WIDE, and MS-COCO. Experimental results demonstrate that the proposed method outperforms the compared methods, and the method is also superior to all previous deep hashing methods based on the triplet label. SN - 1687-5265 UR - https://doi.org/10.1155/2019/8490364 DO - 10.1155/2019/8490364 JF - Computational Intelligence and Neuroscience PB - Hindawi KW - ER -